Impressive progress has been made recently in image-to-image translation using generative adversarial networks (GANs). However, existing methods often fail in translating source images with noise to target domain. To address this problem, we joint image-to-image translation with image denoising and propose an enhanced generative adversarial network (EGAN). In particular, built upon pix2pix, we introduce residual blocks in the generator network to capture deeper multi-level information between source and target image distribution. Moreover, a perceptual loss is proposed to enhance the performance of image-to-image translation. As demonstrated through extensive experiments, our proposed EGAN can alleviate effects of noise in source images, and outperform other state-of-the-art methods significantly. Furthermore, we experimentally indicate that the proposed EGAN is also effective when applied to image denoising.

最近在使用生成对抗网络（GAN）进行图像到图像的翻译方面取得了令人印象深刻的进步。但是，现有方法通常无法将带有噪声的源图像转换到目标域。为了解决这个问题，我们将图像到图像的翻译与图像去噪相结合，并提出了一种增强的生成对抗网络（EGAN）。特别是，在pix2pix的基础上，我们在生成器网络中引入了剩余块，以捕获源图像和目标图像分布之间的更深层次的多层信息。此外，提出了感知损失以增强图像到图像翻译的性能。正如通过大量实验所证明的那样，我们提出的EGAN可以减轻源图像中噪声的影响，并显着优于其他最新方法。此外，